We present a smartwatch application that recognizes important sign sentences. We make use of modern smart watches like Samsung Gear that are equipped with inbuilt sensors including accelerometer, gyroscope and magnetometer. We show how well a smartwatch can recognize important sign sentences. We have implemented a smartwatch app that collects 3d accelerometer and 3d gyroscope data from the watch. We have recorded 8 questions and 13 sentences from 5 people who are fluent in sign language. We use dynamic time warping to compute the distances between the gestures and templates in all data dimensions. The resulting distances serve as input for discriminating the gestures. We evaluated the discriminative ability of logistic regression. In person-independent evaluations, we achieve discrimination accuracies between 85.7% and 97.6%.

Smoking cessation poses a variety of difficulties to smokers, with decreased motivation and awareness being among them. Those specific problems can be addressed by providing persistent motivation and counselling. Considering that the process of smoking cessation usually lasts several weeks, finding a human counsellor for such a prolonged period turns out to be challenging. In this paper, we propose a wearable smoking cessation assistant, SmokeWatch, which monitors its user continuously and detects smoking events. The user is then encouraged to refrain from smoking. We collected data from 26 individuals. We show that our Dynamic Time Warping based smoking detection algorithm has a success rate of 96%. At this stage, we are giving personal advices, e.g. based on the number of detected smoking events we can calculate the money spent for cigarettes.

Dementia is a growing healthcare problem, and it has become necessary to find a way to reduce the prevalence of this disease. Mild cognitive impairment is a risk factor for dementia, and being able to detect the onset of mild cognitive impairment gives healthcare professionals the chance to reduce the effect of dementia on the society. In this paper, we propose a system that seeks to detect mild cognitive impairment in otherwise healthy persons. We are particularly interested in being able to gather data for monitoring without interfering with the subject's daily living.

Weather reports are an integral part of almost any modern newscast service. Concise weather reports, which are often found in mobile applications, consist of logos for indicating sunshine, cloudiness, fog or rain. The weather information is usually obtained from professional weather stations. Sky Map aims to create mobile weather reports based on crowd sourcing of images that contain regions of the sky. The main motivation behind is that observing the sky gives us an intuitive understanding about the weather situation. Sky Map intends to enable sky observations from everywhere. The main working principle is to gather geo-tagged photos taken from mobile/smartphones with the help of crowdsourcing and to present the relevant sky regions on a map. We have developed mobile phone clients for Android and iOS and a server infrastructure that manages the crowd sourcing. We present the overall system design and we show the results of several feasibility studies.

Participatory sensing is a new paradigm that is based on the data collection, such as images, air and noise measurements, through the embedded digital sensors and radios on current smartphones owned by voluntary users. The participants in such a system can either be self-motivated or persuaded through incentives with amounts depending on factors such as quality of the contributed data or sensors, availability, reputation, urgency and priority. In this paper, the problem of selecting a subset of all users to gain the maximum merit is studied in the context of urban sensing optimization. Accordingly, an efficient participant selection, i.e. recruitment, method is proposed that runs online, i.e. without referring to high computational complexity and prohibitive runtime. The performance of our proposal is compared to random selection schemes and observed to outperform the random method in terms of query merits.

The paper presents a novel automatic early warning system to remotely monitor areas of archaeological and cultural interest from the risk of fire. Since these areas have been treasured and tended for very long periods of time, they are usually surrounded by old and valuable vegetation or situated close to forest regions, which exposes them to an increased risk of fire. The proposed system takes advantage of recent advances in multi-sensor surveillance technologies, using optical and infrared cameras, wireless sensor networks capable of monitoring different modalities (e.g. temperature and humidity) as well as local weather stations on the deployment site. The signals collected from these sensors are transmitted to a monitoring centre, which employs intelligent computer vision and pattern recognition algorithms as well as data fusion techniques to automatically analyze sensor information. The system is capable of generating automatic warning signals for local authorities whenever a dangerous situation arises, as well as estimating the propagation of the fire based on the fuel model of the area and other important parameters such as wind speed, slope, and aspect of the ground surface.

Wireless sensor networks promise great success in many areas from environmental monitoring to medical and military applications. Forest fire detection is one of these areas where many of the ongoing WSN research is focused today. Unfortunately, most of these studies choose simulating their proposed solutions instead of doing experiments in real testbed environments, since that kind of setup exposes additional difficulties. Our previous work, named FireSense, proposed a fire detection algorithm, which was shown to be successful in terms of simulation results. In this study, we take FireSense to a real outdoor testbed for further analysis of its effectiveness in terms of various parameters such as link and node failures, topology and physical configuration changes, wind direction, ignition point position and sampling period variations.